balance_rows

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It clearly states this is a read operation ('Get', 'Returns') for verification purposes, which conveys non-destructive intent. However, it doesn't disclose pagination behavior, potential size limits, or whether companyId overrides affect row visibility. Adequate but thin on behavioral detail for a read tool with no annotation safety net.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, efficient, no filler. Front-loaded with the core action and return structure, then a use-case hint. The mention of '10 numeric columns' with the parenthetical breakdown is slightly verbose but informative and earns its place by describing the return shape.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is relatively simple (2 params, no output schema), so the description covers the essentials well. However, without an output schema, the description is the sole source for return structure—it names columns but not types, ordering, or edge cases (empty trial balance, error behavior). For a verification-oriented read tool, slightly more detail on what 'parsed' means and possible failure modes would round it out.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters ('Trial balance UUID' and 'Company UUID overrides STORNO_COMPANY_ID env var'). The description adds the 'parsed rows' and '10 numeric columns' context which clarifies what the tool returns relative to the id parameter. Description meaningfully frames what the id selects, and companyId's override behavior is already richly documented in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('parsed account rows for a trial balance'), and details the return structure (account codes, names, 10 numeric columns). It doesn't explicitly differentiate from sibling tools like balance_list or balance_reprocess, but it's more specific than balance_list. Minor gap in not naming alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description notes it's 'Useful for verifying PDF parsing results,' which gives a use case, but doesn't explicitly state when NOT to use it or how it differs from balance_list, balance_reprocess, or balance_delete siblings. The verification use case implies reading, but no exclusions or alternatives are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.